Back to skill

Security audit

Script to Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Revid script-to-video integration that sends user-provided scripts to Revid as expected, with no hidden persistence or unrelated local access.

Install this only if you are comfortable sending the script text and your Revid API key to Revid's service for rendering. Avoid submitting confidential, regulated, or proprietary scripts unless your organization approves that third-party processing.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs sending the user's full script to www.revid.ai but does not warn that the content leaves the local environment or may contain sensitive, proprietary, or personal information. Users may unknowingly disclose confidential scripts, internal documents, or regulated data to a third-party service, creating privacy, compliance, and data-governance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill hardcodes an English (US) locale in the voice configuration, which can impose a specific language/locale by default. There is no accompanying instruction that users may choose another language or that this skill is intentionally limited to en-US for a documented reason.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The voice configuration hard-codes both a U.S. English voice ID and the language value "en-US". This imposes a specific language/locale choice without any indication of user opt-in or documentation that the skill is intentionally region-specific.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · examples/run.sh (reported line 18)May include surrounding context.

sh
PAYLOAD=$(cat "$PAYLOAD_FILE")
fi

PID=$(curl -fsS https://www.revid.ai/api/public/v3/render \
  -H "Content-Type: application/json" -H "key: $REVID_API_KEY" \
  -d "$PAYLOAD" | jq -r .pid)
echo "pid=$PID"

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This manifest uses a generic workflow label, "script-to-video", without any surrounding constraints or negative examples clarifying when this skill should be invoked versus similar text-to-media tasks. In a manifest file, that kind of broad activation description can lead to unintended routing or ambiguous invocation behavior.

Content

No source excerpt is available for this finding.